maxmax2016/yourtts

语音克隆VITS YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

In our recent paper we propose the YourTTS model. YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-shot multi-speaker and multilingual training. We achieved state-of-the-art (SOTA) results in zero-shot multi-speaker TTS and results comparable to SOTA in zero-shot voice conversion on the VCTK dataset. Additionally, our approach achieves promising results in a target language with a single-speaker dataset, opening possibilities for zero-shot multi-speaker TTS and zero-shot voice conversion systems in low-resource languages. Finally, it is possible to fine-tune the YourTTS model with less than 1 minute of speech and achieve state-of-the-art results in voice similarity and with reasonable quality. This is important to allow synthesis for speakers with a very different voice or recording characteristics from those seen during training.

Audios samples

Visit our website for audio samples.

Implementation

All of our experiments were implemented on the Coqui TTS repo.

Colab Demos

Demo	URL
Zero-Shot TTS	link
Zero-Shot VC	link

Checkpoints

All the released checkpoints are licensed under CC BY-NC-ND 4.0

Model	URL
Speaker Encoder	link
Exp 1. YourTTS-EN(VCTK)	link
Exp 1. YourTTS-EN(VCTK) + SCL	link
Exp 2. YourTTS-EN(VCTK)-PT	link
Exp 2. YourTTS-EN(VCTK)-PT + SCL	link
Exp 3. YourTTS-EN(VCTK)-PT-FR	link
Exp 3. YourTTS-EN(VCTK)-PT-FR SCL	link
Exp 4. YourTTS-EN(VCTK+LibriTTS)-PT-FR SCL	link

Coqui TTS released model

TTS

To use the 🐸 TTS released YourTTS model for Text-to-Speech use the following command:

tts  --text "This is an example!" --model_name tts_models/multilingual/multi-dataset/your_tts  --speaker_wav target_speaker_wav.wav --language_idx "en"

Considering the "target_speaker_wav.wav" an audio sample from the target speaker.

Voice conversion

To use the 🐸 TTS released YourTTS model for voice conversion use the following command:

tts --model_name tts_models/multilingual/multi-dataset/your_tts  --speaker_wav target_speaker_wav.wav --reference_wav  target_content_wav.wav --language_idx "en"

Considering the "target_content_wav.wav" as the reference wave file to convert into the voice of the "target_speaker_wav.wav" speaker.

Results replicability

To insure replicability, we make the audios used to generate the MOS available here. In addition, we provide the MOS for each audio here.

To re-generate our MOS results, follow the instructions here. To predict the test sentences and generate the SECS, please use the Jupyter Notebooks available here.

Test Speakers:

LibriTTS (test clean): 1188, 1995, 260, 1284, 2300, 237, 908, 1580, 121 and 1089

VCTK: p261, p225, p294, p347, p238, p234, p248, p335, p245, p326 and p302

MLS Portuguese: 12710, 5677, 12249, 12287, 9351, 11995, 7925, 3050, 4367 and 13069

Citation

@ARTICLE{2021arXiv211202418C,
  author = {{Casanova}, Edresson and {Weber}, Julian and {Shulby}, Christopher and {Junior}, Arnaldo Candido and {G{\"o}lge}, Eren and {Antonelli Ponti}, Moacir},
  title = "{YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone}",
  journal = {arXiv e-prints},
  keywords = {Computer Science - Sound, Computer Science - Computation and Language, Electrical Engineering and Systems Science - Audio and Speech Processing},
  year = 2021,
  month = dec,
  eid = {arXiv:2112.02418},
  pages = {arXiv:2112.02418},
  archivePrefix = {arXiv},
  eprint = {2112.02418},
  primaryClass = {cs.SD},
  adsurl = {https://ui.adsabs.harvard.edu/abs/2021arXiv211202418C},
  adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}